Manifold Representations for State Estimation in Contact Manipulation

  • Michael C. Koval
  • Nancy S. Pollard
  • Siddhartha S. Srinivasa
Part of the Springer Tracts in Advanced Robotics book series (STAR, volume 114)


We investigate the problem of using contact sensors to estimate the configuration of an object during manipulation. Contact sensing is very discriminative by nature and, therefore, the set of object configurations that activate a sensor constitutes a lower-dimensional manifold in the configuration space of the object. This causes conventional state estimation methods, such as particle filters, to perform poorly during periods of contact. The manifold particle filter addresses this problem by sampling particles directly from the contact manifold. When it exists, we can sample these particles from an analytic representation of the contact manifold. We present two alternative sample-based contact manifold representations that make no assumptions about the object-hand geometry: rejection sampling and trajectory rollouts. We discuss theoretical considerations behind these three representations and compare their performance in a suite of simulation experiments. We show that all three representations enable the manifold particle filter to outperform the conventional particle filter. Additionally, we show that the trajectory rollout representation performs similarly to the analytic method despite the rollout method’s relative simplicity.


Root Mean Square Error Particle Filter Importance Sampling Kernel Density Estimation Belief State 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.



This work was supported by a NASA Space Technology Research Fellowship and the DARPA Autonomous Robotic Manipulation Software Track (ARM-S) program. We would also like to thank Mehmet Dogar, Anca Dragan, and the members of the Personal Robotics Lab for their helpful input.


  1. 1.
    Dogar, M., Hsiao, K., Ciocarlie, M., Srinivasa, S.S.: Physics-based Grasp planning through clutter. In: RSS (2012)Google Scholar
  2. 2.
    Dogar, M.R., Srinivasa, S.S.: Push-grasping with dexterous hands: mechanics and a method. In: IEEE/RSJ IROS (2010)Google Scholar
  3. 3.
    Farahat, A.O., Stiller, P.F., Trinkle, J.C.: On the geometry of contact formation cells for systems of polygons. In: IEEE T-RO (1995)Google Scholar
  4. 4.
    Fishel, J.A., Loeb, G.E.: Sensing tactile microvibrations with the biotac comparison with human sensitivity. In: IEEE/RAS-EMBS BioRob (2012)Google Scholar
  5. 5.
    Jia, Y., Erdmann, M.: Pose and motion from contact. In: IJRR (1999)Google Scholar
  6. 6.
    Koval, M.C., Dogar, M.R., Pollard, N.S., Srinivasa, S.S.: Pose estimation for contact manipulation with manifold particle filters. In: IEEE/RSJ IROS (2013)Google Scholar
  7. 7.
    LaValle, V.M.: Planning Algorithms. Cambridge University Press, Cambridge (2006)CrossRefzbMATHGoogle Scholar
  8. 8.
    Lozano-Pèrez, T.: Spatial Planning: a configuration space approach. In: IEEE T-C (1983)Google Scholar
  9. 9.
    Lynch, K.M.,Maekawa, H., Tanie, K.: Manipulation and active sensing by pushing using tactile feedback. In: IEEE/RSJ IROS (1992)Google Scholar
  10. 10.
    Montemerlo, M., Thrun, S., Koller, D., Wegbreit, B.: FastSLAM 2.0: An improved particle filtering algorithm for simultaneous localization and mapping that provably converges. In: IJCAI (2003)Google Scholar
  11. 11.
    Odhner, L., Jentoft, L.P., Claffee, M.R., Corson, N., Tenzer, Y., Ma, R.R., Buehler, M., Kohout, R., Howe, R.D., Dollar, A.M.: A compliant, underactuated hand for robust manipulation. In: CoRR (2013)Google Scholar
  12. 12.
    Pelletier, B.: Kernel density estimation on Riemannian manifolds. Stat. Prob. Lett. (2005)Google Scholar
  13. 13.
    Rosenblatt, M., et al.: Remarks on some nonparametric estimates of a density function. Ann. Math. Stat. 27, 832–837 (1956)MathSciNetCrossRefzbMATHGoogle Scholar
  14. 14.
    Silverman, B.W.: Using kernel density estimates to investigate multimodality. J. R. Stat. Soc. 43, 97–99 (1981)MathSciNetGoogle Scholar
  15. 15.
    Tenzer, Y., Jentoft, L.P., Howe, R.D.: Inexpensive and Easily customized tactile array sensors using MEMS barometers chips. In: IEEE (2012)Google Scholar
  16. 16.
    Thrun, S., Fox, D., Burgard, W.: Monte Carlo localization with mixture proposal distribution. In: AAAI (2000)Google Scholar
  17. 17.
    Thrun, S., Burgard, W., Fox, D.: Probabilistic Robotics. MIT Press, Cambridge (2005)zbMATHGoogle Scholar
  18. 18.
    Wein, R.: 2D Minkowski Sums. In: CGAL User and Reference Manual. CGAL Editorial Board, 4.3 edition (2013)Google Scholar
  19. 19.
    Zhang, L., Trinkle, J.C.: The application of particle filtering to grasping acquisition with visual occlusion and tactile sensing. In: IEEE ICRA (2012)Google Scholar
  20. 20.
    Zhang, L., Lyu, S., Trinkle, J.: A dynamic bayesian approach to simultaneous estimation and filtering in grasp acquisition. In: IEEE ICRA (2013)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Michael C. Koval
    • 1
  • Nancy S. Pollard
    • 1
  • Siddhartha S. Srinivasa
    • 1
  1. 1.Robotics InstituteCarnegie Mellon UniversityPittsburghUSA

Personalised recommendations